INDEX

Explanations

the name "Alexander" in various contexts

oai_token-act-pair · gpt-3.5-turbo

mentions of the name "Alexander."

oai_token-act-pair · gpt-4o-mini Triggered by @bot

New Auto-Interp

Top Features by Cosine Similarity

Comparing With GPT2-SMALL @ 0-res-jb

Configuration

jbloom/GPT2-Small-SAEs-Reformatted/blocks.0.hook_resid_pre

Prompts (Dashboard)

24,576 prompts, 128 tokens each

Dataset (Dashboard)

Skylion007/openwebtext

Features

24,576

Data Type

torch.float32

Hook Point

blocks.0.hook_resid_pre

Architecture

standard

Context Size

128

Dataset

Skylion007/openwebtext

Hook Point Layer

Activation Function

relu

Embeds

PlotsExplanationShow Test FieldDefault Test Text

IFrame

Link

Not in Any Lists

No Comments

Negative Logits

tub

-0.78

eals

-0.75

swing

-0.75

suc

-0.71

 warped

-0.70

isec

-0.68

Switch

-0.66

Wii

-0.66

 surf

-0.66

 recy

-0.65

POSITIVE LOGITS

 Alexander

3.64

Alexander

2.99

ALE

1.48

 Anton

1.38

 Alexandra

1.37

 Maced

1.35

 Alex

1.31

 Alexis

1.24

 Igor

1.23

 Darius

1.22

Activations Density 0.013%

the name "Alexander" in various contexts

mentions of the name "Alexander."

No Comments

No Known Activations